HUSTbearing dataset

Dataset Overview

• Name: HUSTbearing dataset
• Type: Open‑source dataset
• Content: Contains vibration signals from bearings in 9 different health states, collected under 11 different operating conditions.
• Use: Intended for validating the effectiveness of rolling‑bearing fault diagnosis algorithms.
• Citation requirement: Works using this dataset should cite the paper: Chao Zhao, Enrico Zio, Weiming Shen, Domain Generalization for Cross‑Domain Fault Diagnosis: an Application‑oriented Perspective and a Benchmark Study, Reliability Engineering and System Safety (2024), DOI: https://doi.org/10.1016/j.ress.2024.109964.

Experimental Details

• Test equipment: Bearings were tested using a Spectra‑Quest Mechanical Fault Simulator.
• Bearing health states: Includes normal condition and 8 fault conditions:
  • Normal
  • Medium inner‑ring fault
  • Severe inner‑ring fault
  • Medium outer‑ring fault
  • Severe outer‑ring fault
  • Medium ball fault
  • Severe ball fault
  • Medium combined fault (inner + outer)
  • Severe combined fault (inner + outer)
• Test bearing model: ER‑16K
• Bearing parameters:
  • Shaft diameter: 38.52 mm
  • Ball diameter: 7.94 mm
  • Number of balls: 9
• Operating conditions: 11 conditions covering frequencies from 20 Hz to 80 Hz and a variable speed profile of 0‑40‑0 Hz.
• Sampling settings:
  • Sampling frequency: 25.6 kHz
  • Samples per acquisition: 262 144 (≈ 10.2 s)

Dataset Details

• File format: Excel
• Number of files: 99 (9 health states × 11 operating conditions)
• File naming rule: e.g., 0.5X_B_65Hz denotes a medium ball fault under a 65 Hz condition; 0.5X indicates medium damage.
• Health‑state codes:
  • H: Healthy
  • I: Inner‑ring fault
  • O: Outer‑ring fault
  • B: Ball fault
  • C: Combined fault

Contact Information

• Contact person: Chao Zhao